© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65536
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Én
    -1.02
     those
    -0.93
     práticas
    -0.91
    tadi
    -0.85
    ایب
    -0.84
     hatt
    -0.84
     kommende
    -0.81
     kaffe
    -0.80
     ){
    -0.80
    anzibar
    -0.80
    POSITIVE LOGITS
    ativité
    0.93
     拡大
    0.86
     search
    0.82
     sirve
    0.82
     lightest
    0.80
     return
    0.79
    vee
    0.79
    ҙ
    0.79
     بدون
    0.78
     genealogy
    0.78
    Activations Density 0.013%

    No Known Activations